TexTeller v2

src/models/ocr_model/model/TexTeller.py

@@ -17,7 +17,7 @@ from transformers import (
 
 
 class TexTeller(VisionEncoderDecoderModel):
-    REPO_NAME = '/home/lhy/code/TexTeller/src/models/ocr_model/train/train_result/TexTellerv2/checkpoint-356000'
+    REPO_NAME = '/home/lhy/code/TexTeller/src/models/ocr_model/train/train_result/TexTellerv2/checkpoint-588000'
     def __init__(self, decoder_path=None, tokenizer_path=None):
         encoder = ViTModel(ViTConfig(
             image_size=FIXED_IMG_SIZE,

src/start_web.sh

@@ -3,7 +3,8 @@ set -exu
 
 export CHECKPOINT_DIR="default"
 export TOKENIZER_DIR="default"
-export USE_CUDA=False  # True or False (case-sensitive)
-export NUM_BEAM=1
+# export USE_CUDA=False  # True or False (case-sensitive)
+export USE_CUDA=True  # True or False (case-sensitive)
+export NUM_BEAM=10
 
 streamlit run web.py

src/web.py

@@ -95,7 +95,7 @@ def rendering(formula: str, out_img_path: Path) -> bool:
     return p.returncode == 0
 
 def pdf_to_pngbytes(pdf_path):
-    images = convert_from_path(pdf_path, first_page=1, last_page=1)
+    images = convert_from_path(pdf_path, dpi=400,first_page=1, last_page=1)
     trimmed_images = trim(images[0])
     png_image_bytes = io.BytesIO()
     trimmed_images.save(png_image_bytes, format='PNG')